Loss Functions

Randomization Can Reduce Both Bias and Variance: A Case Study in Random Forests JMLR 2025 Real-World Summarization: When Evaluation Reaches Its Limits EMNLP 2025 Reassessing How to Compare and Improve the Calibration of Machine Learning Models ICLR 2025 Regretful Decisions under Label Noise ICLR 2025 Regularizing Energy among Training Samples for Out-of-Distribution Generalization ICLR 2025 Reinforcement Learning for Large Language Models via Group Preference Reward Shaping EMNLP 2025 ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning EMNLP 2025 Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off ICLR 2025 Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models COLING 2025 Rethinking Reward Modeling in Preference-based Large Language Model Alignment ICLR 2025 Revisiting Interpolation for Noisy Label Correction AAAI 2025 REvolve: Reward Evolution with Large Language Models using Human Feedback ICLR 2025 RSSN at SemEval-2025 Task 11: Optimizing Multi-Label Emotion Detection with Transformer-Based Models and Threshold Tuning SemEval 2025 R-VLM: Region-Aware Vision Language Model for Precise GUI Grounding ACL 2025 Self-Supervised Learning with Spectral Low-Rank Prior for Hyperspectral Image Reconstruction WACV 2025 SLACE: A Monotone and Balance-Sensitive Loss Function for Ordinal Regression AAAI 2025 STAR: Stability-Inducing Weight Perturbation for Continual Learning ICLR 2025 Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target. CVPR 2025 Structural Entropy Guided Probabilistic Coding AAAI 2025 Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation ICCV 2025 T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning CVPR 2025 The Impact Label Noise and Choice of Threshold has on Cross-Entropy and Soft-Dice in Image Segmentation CVPR 2025 The KoLMogorov Test: Compression by Code Generation ICLR 2025 ThinkAnswer Loss: Balancing Semantic Similarity and Exact Matching for LLM Reasoning Enhancement EMNLP 2025 Token Weighting for Long-Range Language Modeling NAACL 2025